You are on page 1of 16

Deep Learning

computer vision and image recognition.

Applications
of
Convolutional
Neural
Networks
GVHD: DR. NGUYỄN MINH ĐỨC

TRẦN QUỐC HƯNG_20192897


I. Introduction

II. Applicants

OUTLINE
 III. Disadvantages

IV. Conclusion
Why I choose topic?
• The convolutional neural networks
(CNN) is one of the most successful
deep learning model in the field of
face recognition, the different
image regions are always treated
equally when extracting image
features, but in fact different parts
of the face play different roles in
face recognition.

• It’s used in picture procession


system of Facebook, Google,
Amazon,….
Applications of Convolutional Neural Networks

1. Decoding Facial Recognition

2. Analyzing Documents

3. Historic and Environmental


Collections

4. Understanding
Climate
5. Grey Areas
6. Advertising
Applications: Face Recognition, Image Classification..

I. Smart Attendance Management System Based on


Face Recognition Using CNN

• Social Media, Identification,


and Surveillance

• Tracking Locations
II. Implementation on
Smart Glasses .
• Security,

• Law enforcement agencies, Suspect


Identification,

• Portability and good frontal view


capturing, 98%...

https://www.semanticscholar.org/paper/Facial-Recognition-using-Convolutional-Neural-and-Khan-Javed/
III. Monitoring Asphalt Pavement Aging and Damage Conditions from Low-
Altitude UAV Imagery Based on a CNN Approach

https://www.semanticscholar.org/paper/Monitoring-Asphalt-Pavement-Aging-and-Damage-from-a-
Pan-Chen/
IV. Enhancement of Patient Facial
Recognition through CNN.
• Medical,

• Facial expression recognition and patient


monitoring,

•X-ray and MRI images

https://www.semanticscholar.org/paper/Enhancement-of-Patient-Facial-Recognition
V. Multi-Classification of Brain Tumor MRI Images Using Deep Convolutional
Neural Network with Fully Optimized Framework

https://www.semanticscholar.org/paper/Multi-Classification-of-Brain-Tumor-MRI-Images-Deep-Irmak/963d73e7d46725d462dfa5060ecf9e44fc005f97
VI. Finger-vein biometric identification using convolutional neural network
• Biometric techniques
• Finger-vein
• Reduce data dimensionality
• An identification rate of 100.00% is achieved

https://www.semanticscholar.org/paper/Finger-vein-biometric-identification-using-neural-Radzi-Khalil-Hani
Benefits of employing CNNs
The benefits of using CNNs over other traditional neural networks in the
computer vision environment are listed as follows:
• The main reason to consider CNN is the weight sharing feature, which
reduces the number of trainable network parameters and in turn helps the
network to enhance generalization and to avoid overfitting.
• Concurrently learning the feature extraction layers and the classification
layer causes the model output to be both highly organized and highly reliant
on the extracted features.
• Large-scale network implementation is much easier with CNN than with
other neural networks.
• ....
Disadvantages of CNN models
• Classification of Images with different Positions:

To a CNN both the above pictures are almost


similar as both contain the same contents.
• Adversarial examples

• Coordinate Frame
• Takes a long time, How we
can reduce computation in
CNN models?

• Complex, Difficulty in coding


convolutional neural
networks Difficulty in convolutiona
l neural networks
• Performance with low-
quality image
Conclusion

• Wide variety of applications.

• Which is just one of many amazing examples of how artificial neural networks are
making the world a better place.

• However, there are some drawbacks of CNN models which we have covered and
attempts to fix it.
Thank you

You might also like